Machine Learning-based Alzheimer’s Disease Prediction using Personalized Methods

Alzheimer’s disease (AD) is a neurological illness which occurs over time. Early detection reduces the likelihood of disease worsening condition. Unfortunately, the present research focuses on defining disease processes in their existing stages rather than forecasting disease progression. The Generative Personalized embedding model (GPE) is a multi-layer perceptron that is proficient of relating prior knowledge to the prediction process by realizing the patient’s behavioural data and helps in forecasting the disease progression. This work suggest a prediction process based on GPE. As a result, a GPA network is built with the connectivity layers and activated layers to observe the possible correlation among information and next generation of Alzheimer’s disease. Experiments reveal that the outcomes significantly outperformed the majority of previous designs.